© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22868
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    だけは
    -0.89
    WebElementEntity
    -0.89
     suoi
    -0.89
    事です
    -0.88
    Créditos
    -0.88
     voltak
    -0.86
     bluza
    -0.86
    Всё
    -0.85
     impreso
    -0.85
     tatou
    -0.85
    POSITIVE LOGITS
    1
    1.12
    큰
    1.02
     автомобиль
    0.99
    面对
    0.98
    ability
    0.95
    可以说
    0.91
    })`
    0.89
    料金
    0.88
    hasMore
    0.88
    =").
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.